{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Feature based Light Curve Classification\n", "**Written by:** Christopher Wells (SUNY Oswego), Ashish Mahabal (Caltech)\n", "\n", "\n", "**Dependencies:**\n", "- numpy (1.11.1)\n", "- pandas (0.20.3)\n", "- matplotlib (2.0.2)\n", "- seaborn (0.8)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We will use data on periodic variables from CRTS (https://arxiv.org/abs/1405.4290)\n", "There are ~50,000 objects, in ~17 classes. We will learn about Light Curves (== Time Series), and one way of classifying them - using features. (Accompanying slides).\n", "\n", "In this notebook we will use a subset of that dataset with only a few classes, and only a few features. You should use the bigger dataset, and more features.\n", "\n", "First let's load in the catalog data. The catalog contains the ids for the light curves and a few different classes of periodic variable." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | id | \n", "category | \n", "
---|---|---|
0 | \n", "1132001045263 | \n", "beta Lyrae | \n", "
1 | \n", "1012001026394 | \n", "RRab | \n", "
2 | \n", "1143001058200 | \n", "RRab | \n", "
3 | \n", "1018001037204 | \n", "RRab | \n", "
4 | \n", "1012002050063 | \n", "beta Lyrae | \n", "
5 | \n", "1143001077142 | \n", "RRab | \n", "
6 | \n", "1126001058284 | \n", "EA_UP | \n", "
7 | \n", "1009002011733 | \n", "RRab | \n", "
8 | \n", "1012002037935 | \n", "RRab | \n", "
9 | \n", "1018002043699 | \n", "RRab | \n", "
10 | \n", "1123002019791 | \n", "beta Lyrae | \n", "
11 | \n", "1018002041429 | \n", "LPV | \n", "
12 | \n", "1015002015607 | \n", "RRab | \n", "
13 | \n", "1007002017208 | \n", "RRab | \n", "
14 | \n", "1138002064434 | \n", "RRab | \n", "
15 | \n", "1143002089866 | \n", "RRab | \n", "
16 | \n", "1126002018411 | \n", "RRab | \n", "
17 | \n", "1009002014299 | \n", "RRab | \n", "
18 | \n", "1009002022770 | \n", "RRab | \n", "
19 | \n", "1009002023593 | \n", "RRab | \n", "
20 | \n", "1018002024540 | \n", "LPV | \n", "
21 | \n", "1129002035163 | \n", "beta Lyrae | \n", "
22 | \n", "1004003007536 | \n", "LPV | \n", "
23 | \n", "1004003047047 | \n", "RRab | \n", "
24 | \n", "1112002022226 | \n", "RRab | \n", "
25 | \n", "1143002005470 | \n", "RRab | \n", "
26 | \n", "1138002068806 | \n", "EA_UP | \n", "
27 | \n", "1132002041787 | \n", "beta Lyrae | \n", "
28 | \n", "1135002048623 | \n", "RRab | \n", "
29 | \n", "1015003044944 | \n", "RRab | \n", "
... | \n", "... | \n", "... | \n", "
370 | \n", "1135033079131 | \n", "EA_UP | \n", "
371 | \n", "1138032092140 | \n", "EA_UP | \n", "
372 | \n", "1121039083958 | \n", "EA_UP | \n", "
373 | \n", "1138033017562 | \n", "EA_UP | \n", "
374 | \n", "1132036013362 | \n", "EA_UP | \n", "
375 | \n", "1138035017530 | \n", "EA_UP | \n", "
376 | \n", "1104043031307 | \n", "EA_UP | \n", "
377 | \n", "1149029061534 | \n", "EA_UP | \n", "
378 | \n", "1112043077642 | \n", "EA_UP | \n", "
379 | \n", "1138035036691 | \n", "EA_UP | \n", "
380 | \n", "1140034027271 | \n", "EA_UP | \n", "
381 | \n", "1001044045564 | \n", "EA_UP | \n", "
382 | \n", "1143033047478 | \n", "EA_UP | \n", "
383 | \n", "1001045092189 | \n", "EA_UP | \n", "
384 | \n", "1007046006121 | \n", "EA_UP | \n", "
385 | \n", "1009046074714 | \n", "EA_UP | \n", "
386 | \n", "1104047005997 | \n", "EA_UP | \n", "
387 | \n", "1007047069269 | \n", "EA_UP | \n", "
388 | \n", "1112047057788 | \n", "EA_UP | \n", "
389 | \n", "1126043006161 | \n", "EA_UP | \n", "
390 | \n", "1118046021257 | \n", "EA_UP | \n", "
391 | \n", "1107047046184 | \n", "EA_UP | \n", "
392 | \n", "1123044022189 | \n", "EA_UP | \n", "
393 | \n", "1138039038111 | \n", "EA_UP | \n", "
394 | \n", "1004048073006 | \n", "EA_UP | \n", "
395 | \n", "1152031059450 | \n", "EA_UP | \n", "
396 | \n", "1009049001498 | \n", "EA_UP | \n", "
397 | \n", "1135042033190 | \n", "EA_UP | \n", "
398 | \n", "1146037011758 | \n", "EA_UP | \n", "
399 | \n", "1015053020309 | \n", "EA_UP | \n", "
400 rows × 2 columns
\n", "\n", " | ampl | \n", "br_fa | \n", "famp | \n", "mad | \n", "stet_K | \n", "totvar | \n", "id | \n", "category | \n", "
---|---|---|---|---|---|---|---|---|
0 | \n", "2.848828 | \n", "1.537394 | \n", "7.093844 | \n", "0.014893 | \n", "0.325150 | \n", "2.185123 | \n", "1132001045263 | \n", "beta Lyrae | \n", "
1 | \n", "0.731702 | \n", "1.138012 | \n", "8.554225 | \n", "0.205786 | \n", "0.808286 | \n", "2.626196 | \n", "1012001026394 | \n", "RRab | \n", "
2 | \n", "0.079379 | \n", "1.577254 | \n", "6.531317 | \n", "0.024936 | \n", "0.821861 | \n", "1.252995 | \n", "1143001058200 | \n", "RRab | \n", "
3 | \n", "1.485876 | \n", "0.789104 | \n", "8.864455 | \n", "0.365766 | \n", "0.737108 | \n", "2.424899 | \n", "1018001037204 | \n", "RRab | \n", "
4 | \n", "0.300673 | \n", "0.230666 | \n", "7.284239 | \n", "0.055182 | \n", "0.768989 | \n", "2.147134 | \n", "1012002050063 | \n", "beta Lyrae | \n", "
5 | \n", "1.113359 | \n", "1.176916 | \n", "8.093571 | \n", "0.206672 | \n", "0.806348 | \n", "1.316876 | \n", "1143001077142 | \n", "RRab | \n", "
6 | \n", "0.364004 | \n", "0.066938 | \n", "7.439895 | \n", "0.027766 | \n", "0.611048 | \n", "1.896632 | \n", "1126001058284 | \n", "EA_UP | \n", "
7 | \n", "0.792099 | \n", "1.093868 | \n", "8.195112 | \n", "0.206261 | \n", "0.791534 | \n", "2.142767 | \n", "1009002011733 | \n", "RRab | \n", "
8 | \n", "0.656046 | \n", "1.124566 | \n", "8.231025 | \n", "0.173738 | \n", "0.790750 | \n", "2.606791 | \n", "1012002037935 | \n", "RRab | \n", "
9 | \n", "0.634423 | \n", "3.014010 | \n", "7.697300 | \n", "0.180788 | \n", "0.824355 | \n", "2.211113 | \n", "1018002043699 | \n", "RRab | \n", "
10 | \n", "0.575132 | \n", "0.555603 | \n", "8.281407 | \n", "0.106278 | \n", "0.821908 | \n", "2.434023 | \n", "1123002019791 | \n", "beta Lyrae | \n", "
11 | \n", "0.800654 | \n", "0.668413 | \n", "6.757894 | \n", "0.336547 | \n", "0.865043 | \n", "2.052597 | \n", "1018002041429 | \n", "LPV | \n", "
12 | \n", "0.907082 | \n", "2.383302 | \n", "8.089449 | \n", "0.118120 | \n", "0.594487 | \n", "1.744148 | \n", "1015002015607 | \n", "RRab | \n", "
13 | \n", "1.186781 | \n", "0.887985 | \n", "8.521211 | \n", "0.318454 | \n", "0.768737 | \n", "2.320403 | \n", "1007002017208 | \n", "RRab | \n", "
14 | \n", "0.313629 | \n", "1.123481 | \n", "7.774146 | \n", "0.074781 | \n", "0.842069 | \n", "1.929035 | \n", "1138002064434 | \n", "RRab | \n", "
15 | \n", "0.432890 | \n", "1.220354 | \n", "7.866900 | \n", "0.189535 | \n", "0.850135 | \n", "1.406795 | \n", "1143002089866 | \n", "RRab | \n", "
16 | \n", "0.990914 | \n", "1.515920 | \n", "8.485751 | \n", "0.225957 | \n", "0.787120 | \n", "2.184664 | \n", "1126002018411 | \n", "RRab | \n", "
17 | \n", "0.327898 | \n", "1.020639 | \n", "8.024524 | \n", "0.095169 | \n", "0.826693 | \n", "2.111490 | \n", "1009002014299 | \n", "RRab | \n", "
18 | \n", "1.872920 | \n", "5.765435 | \n", "7.940280 | \n", "0.071828 | \n", "0.550917 | \n", "2.105432 | \n", "1009002022770 | \n", "RRab | \n", "
19 | \n", "1.388025 | \n", "1.540907 | \n", "7.995671 | \n", "0.131704 | \n", "0.772002 | \n", "1.985445 | \n", "1009002023593 | \n", "RRab | \n", "
20 | \n", "1.358454 | \n", "0.801392 | \n", "5.913152 | \n", "0.722918 | \n", "0.887361 | \n", "1.864518 | \n", "1018002024540 | \n", "LPV | \n", "
21 | \n", "1.036067 | \n", "0.161247 | \n", "7.126598 | \n", "0.083789 | \n", "0.807215 | \n", "2.345246 | \n", "1129002035163 | \n", "beta Lyrae | \n", "
22 | \n", "0.425579 | \n", "0.501925 | \n", "6.344272 | \n", "0.128586 | \n", "0.868455 | \n", "1.470957 | \n", "1004003007536 | \n", "LPV | \n", "
23 | \n", "1.637094 | \n", "1.220023 | \n", "8.734181 | \n", "0.331210 | \n", "0.684890 | \n", "1.763744 | \n", "1004003047047 | \n", "RRab | \n", "
24 | \n", "1.395042 | \n", "1.672418 | \n", "7.851418 | \n", "0.119590 | \n", "0.709399 | \n", "1.822527 | \n", "1112002022226 | \n", "RRab | \n", "
25 | \n", "0.519883 | \n", "2.063397 | \n", "7.814018 | \n", "0.163623 | \n", "0.818896 | \n", "1.418126 | \n", "1143002005470 | \n", "RRab | \n", "
26 | \n", "0.323481 | \n", "0.028353 | \n", "6.457040 | \n", "0.012392 | \n", "0.589714 | \n", "1.731898 | \n", "1138002068806 | \n", "EA_UP | \n", "
27 | \n", "0.412587 | \n", "0.184503 | \n", "6.782960 | \n", "0.050052 | \n", "0.755415 | \n", "2.267641 | \n", "1132002041787 | \n", "beta Lyrae | \n", "
28 | \n", "1.495231 | \n", "1.220816 | \n", "8.509023 | \n", "0.324616 | \n", "0.788055 | \n", "2.192512 | \n", "1135002048623 | \n", "RRab | \n", "
29 | \n", "0.289190 | \n", "1.431638 | \n", "7.936934 | \n", "0.102801 | \n", "0.835194 | \n", "1.846853 | \n", "1015003044944 | \n", "RRab | \n", "
... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "... | \n", "
370 | \n", "0.896367 | \n", "0.007213 | \n", "6.508964 | \n", "0.011354 | \n", "0.477155 | \n", "2.055363 | \n", "1135033079131 | \n", "EA_UP | \n", "
371 | \n", "0.419296 | \n", "0.126953 | \n", "7.177330 | \n", "0.042490 | \n", "0.651774 | \n", "1.756105 | \n", "1138032092140 | \n", "EA_UP | \n", "
372 | \n", "0.197241 | \n", "0.027914 | \n", "6.815824 | \n", "0.008262 | \n", "0.589664 | \n", "2.254924 | \n", "1121039083958 | \n", "EA_UP | \n", "
373 | \n", "0.261239 | \n", "0.032037 | \n", "7.211568 | \n", "0.010379 | \n", "0.503062 | \n", "2.302154 | \n", "1138033017562 | \n", "EA_UP | \n", "
374 | \n", "0.360921 | \n", "0.021329 | \n", "6.871241 | \n", "0.011770 | \n", "0.515368 | \n", "2.407363 | \n", "1132036013362 | \n", "EA_UP | \n", "
375 | \n", "0.417387 | \n", "0.083004 | \n", "7.266501 | \n", "0.029865 | \n", "0.541180 | \n", "2.886376 | \n", "1138035017530 | \n", "EA_UP | \n", "
376 | \n", "0.412549 | \n", "0.081509 | \n", "6.339859 | \n", "0.028209 | \n", "0.656094 | \n", "2.054074 | \n", "1104043031307 | \n", "EA_UP | \n", "
377 | \n", "0.295883 | \n", "0.046104 | \n", "6.817011 | \n", "0.012863 | \n", "0.514790 | \n", "2.149455 | \n", "1149029061534 | \n", "EA_UP | \n", "
378 | \n", "0.349491 | \n", "0.042801 | \n", "7.436605 | \n", "0.023173 | \n", "0.520201 | \n", "2.573030 | \n", "1112043077642 | \n", "EA_UP | \n", "
379 | \n", "0.376536 | \n", "0.041077 | \n", "6.964064 | \n", "0.014331 | \n", "0.513256 | \n", "2.766948 | \n", "1138035036691 | \n", "EA_UP | \n", "
380 | \n", "0.506562 | \n", "0.130980 | \n", "7.973381 | \n", "0.037456 | \n", "0.612333 | \n", "2.279391 | \n", "1140034027271 | \n", "EA_UP | \n", "
381 | \n", "0.377970 | \n", "0.032257 | \n", "6.715302 | \n", "0.026659 | \n", "0.648923 | \n", "1.696161 | \n", "1001044045564 | \n", "EA_UP | \n", "
382 | \n", "0.277961 | \n", "0.051112 | \n", "6.433125 | \n", "0.017936 | \n", "0.563491 | \n", "2.136027 | \n", "1143033047478 | \n", "EA_UP | \n", "
383 | \n", "0.382161 | \n", "0.034219 | \n", "7.344794 | \n", "0.020747 | \n", "0.648278 | \n", "1.933114 | \n", "1001045092189 | \n", "EA_UP | \n", "
384 | \n", "0.245015 | \n", "0.085321 | \n", "6.997866 | \n", "0.027712 | \n", "0.605064 | \n", "1.667617 | \n", "1007046006121 | \n", "EA_UP | \n", "
385 | \n", "0.471509 | \n", "0.119290 | \n", "7.533602 | \n", "0.046932 | \n", "0.775054 | \n", "2.016895 | \n", "1009046074714 | \n", "EA_UP | \n", "
386 | \n", "0.566807 | \n", "0.097473 | \n", "7.754612 | \n", "0.030658 | \n", "0.572333 | \n", "2.633100 | \n", "1104047005997 | \n", "EA_UP | \n", "
387 | \n", "0.707351 | \n", "0.030574 | \n", "7.360150 | \n", "0.030316 | \n", "0.538448 | \n", "2.408784 | \n", "1007047069269 | \n", "EA_UP | \n", "
388 | \n", "0.388586 | \n", "0.040992 | \n", "7.290711 | \n", "0.023228 | \n", "0.543576 | \n", "2.007269 | \n", "1112047057788 | \n", "EA_UP | \n", "
389 | \n", "0.819318 | \n", "0.122195 | \n", "7.590072 | \n", "0.026526 | \n", "0.521907 | \n", "2.698568 | \n", "1126043006161 | \n", "EA_UP | \n", "
390 | \n", "0.329469 | \n", "0.011369 | \n", "6.886696 | \n", "0.011727 | \n", "0.443763 | \n", "2.542726 | \n", "1118046021257 | \n", "EA_UP | \n", "
391 | \n", "0.247776 | \n", "0.026733 | \n", "7.026692 | \n", "0.009018 | \n", "0.449259 | \n", "2.212594 | \n", "1107047046184 | \n", "EA_UP | \n", "
392 | \n", "0.432277 | \n", "0.088668 | \n", "6.678817 | \n", "0.044423 | \n", "0.592197 | \n", "2.685007 | \n", "1123044022189 | \n", "EA_UP | \n", "
393 | \n", "0.324228 | \n", "0.080468 | \n", "7.256372 | \n", "0.022678 | \n", "0.591981 | \n", "2.475961 | \n", "1138039038111 | \n", "EA_UP | \n", "
394 | \n", "0.297873 | \n", "0.041727 | \n", "7.214062 | \n", "0.020344 | \n", "0.625370 | \n", "2.211250 | \n", "1004048073006 | \n", "EA_UP | \n", "
395 | \n", "0.427949 | \n", "0.070803 | \n", "7.045288 | \n", "0.022769 | \n", "0.754521 | \n", "1.882516 | \n", "1152031059450 | \n", "EA_UP | \n", "
396 | \n", "0.458136 | \n", "0.031402 | \n", "7.475574 | \n", "0.026077 | \n", "0.703121 | \n", "1.464589 | \n", "1009049001498 | \n", "EA_UP | \n", "
397 | \n", "0.360456 | \n", "0.080945 | \n", "6.368060 | \n", "0.031401 | \n", "0.620174 | \n", "1.566059 | \n", "1135042033190 | \n", "EA_UP | \n", "
398 | \n", "0.220151 | \n", "0.098842 | \n", "6.697943 | \n", "0.010453 | \n", "0.626902 | \n", "2.025031 | \n", "1146037011758 | \n", "EA_UP | \n", "
399 | \n", "0.308493 | \n", "0.142039 | \n", "7.535578 | \n", "0.029386 | \n", "0.622929 | \n", "1.904903 | \n", "1015053020309 | \n", "EA_UP | \n", "
400 rows × 8 columns
\n", "